BACKGROUND: Prompt engineering, focusing on crafting effective prompts to large language models (LLMs), has garnered attention for its capabilities at harnessing the potential of LLMs. This is even more crucial in the medical domain due to its specialized terminology and language technicity. Clinical natural language processing applications must navigate complex language and ensure privacy compliance. Prompt engineering offers a novel approach by designing tailored prompts to guide models in exploiting clinically relevant information from complex medical texts. Despite its promise, the efficacy of prompt engineering in the medical domain remains to be fully explored.
OBJECTIVE: The aim of the study is to review research efforts and technical approaches in prompt engineering for medical applications as well as provide an overview of opportunities and challenges for clinical practice.
METHODS: Databases indexing the fields of medicine, computer science, and medical informatics were queried in order to identify relevant published papers. Since prompt engineering is an emerging field, preprint databases were also considered. Multiple data were extracted, such as the prompt paradigm, the involved LLMs, the languages of the study, the domain of the topic, the baselines, and several learning, design, and architecture strategies specific to prompt engineering. We include studies that apply prompt engineering-based methods to the medical domain, published between 2022 and 2024, and covering multiple prompt paradigms such as prompt learning (PL), prompt tuning (PT), and prompt design (PD).
RESULTS: We included 114 recent prompt engineering studies. Among the 3 prompt paradigms, we have observed that PD is the most prevalent (78 papers). In 12 papers, PD, PL, and PT terms were used interchangeably. While ChatGPT is the most commonly used LLM, we have identified 7 studies using this LLM on a sensitive clinical data set. Chain-of-thought, present in 17 studies, emerges as the most frequent PD technique. While PL and PT papers typically provide a baseline for evaluating prompt-based approaches, 61% (48/78) of the PD studies do not report any nonprompt-related baseline. Finally, we individually examine each of the key prompt engineering-specific information reported across papers and find that many studies neglect to explicitly mention them, posing a challenge for advancing prompt engineering research.
CONCLUSIONS: In addition to reporting on trends and the scientific landscape of prompt engineering, we provide reporting guidelines for future studies to help advance research in the medical field. We also disclose tables and figures summarizing medical prompt engineering papers available and hope that future contributions will leverage these existing works to better advance the field.

BACKGROUND: The Department of Veterans Affairs (VA), the largest nationally integrated health system in the United States, is transitioning from its homegrown electronic health record (EHR) to a new vendor-based EHR, Oracle Cerner. Experiences of the first VA site to transition have been widely discussed in the media, but in-depth accounts based on rigorous research are lacking.
OBJECTIVE: We sought to explore employee perspectives on the rationale for, and value of, transitioning from a VA-tailored EHR to a vendor-based product.
METHODS: As part of a larger mixed methods, multisite, formative evaluation of VA clinician and staff experiences with the EHR transition, we conducted semistructured interviews at the Mann-Grandstaff VA Medical Center before, during, and after going live in October 2020. In total, we completed 122 interviews with 26 participants across multiple departments.
RESULTS: Before the new vendor-based EHR went live, participants initially expressed cautious optimism about the transition. However, in subsequent interviews following the go-live, participants increasingly critiqued the vendor\'s understanding of VA\'s needs, values, and workflows, as well as what they perceived as an inadequate fit between the functionalities of the new vendor-based EHR system and VA\'s characteristic approach to care. As much as a year after going live, participants reiterated these concerns while also expressing a desire for substantive changes to the transition process, with some questioning the value of continuing with the transition.
CONCLUSIONS: VA\'s transition from a homegrown EHR to a vendor-based EHR system has presented substantial challenges, both practical and cultural in nature. Consequently, it is a valuable case study for understanding the sociotechnical dimension of EHR-to-EHR transitions. These findings have implications for both VA leadership and the broader community of policy makers, vendors, informaticists, and others involved in large-scale health information technology implementations.

Background: The use of information and communication technology such as telemedicine occupies nowadays a huge place in modern medicine practice all over the world, mainly after the COVID-19 pandemic. However, its implementation in Tunisia and other developing countries has achieved little success with low utilization and can be challenging for several reasons. In this study, our aim was to assess the knowledge, attitudes and practice of Tunisian medical doctors regarding telemedicine. Methods: This was a cross-sectional web survey, administered to medical doctors in Tunisia in October 2022. Respondents\' level of knowledge of telemedicine was assessed by calculating a knowledge score (0 to 12). Attitude subsections were about perceived telemedicine attributes of relative advantage, compatibility, trial ability and complexity. Results: A total of 243 participants were included. The mean age was 45 ± 9.6 years old, and 57.2% were female, with a mean of 14.3 ± 10.3 years of professional experience. The majority (95.9%) had an average or high level of computer skills. More than half (59.3%) had a poor level of telemedicine knowledge. A good level of knowledge was significantly associated with age category over 50 years (p = 0.02) and with years of experience over 10 (p = 0.03). The majority (89.3%) had a moderate or high score about perceived advantages. The majority (88.5%) accepted use of telemedicine in their future practice. Almost half (46.9%) had practiced telemedicine activities before using a mobile phone (91%) or social media (64%). The principal limitations of applying telemedicine were challenges of organization and implementation, and incomplete patient examination. Conclusions: Although Tunisian doctors\' knowledge and practice of telemedicine were unsatisfactory, their positive attitude and willingness to try it in their future practice were encouraging. There is an urgent need for implementing telemedicine in Tunisia to improve health care coverage in some unprivileged areas.

BACKGROUND: The Medical Informatics Initiative (MII) in Germany has pioneered platforms such as the National Portal for Medical Research Data (FDPG) to enhance the accessibility of data from clinical routine care for research across both university and non-university healthcare settings. This study explores the efficacy of the Medical Informatics Hub in Saxony (MiHUBx) services by integrating Klinikum Chemnitz gGmbH (KC) with the FDPG, leveraging the Fast Healthcare Interoperability Resources Core Data Set of the MII to standardize and harmonize data from disparate source systems.
METHODS: The employed procedures include deploying installation packages to convert data into FHIR format and utilizing the Research Data Repository for structured data storage and exchange within the clinical infrastructure of KC.
RESULTS: Our results demonstrate successful integration, the development of a comprehensive deployment diagram, additionally, it was demonstrated that the non-university site can report clinical data to the FDPG.
CONCLUSIONS: The discussion reflects on the practical application of this integration, highlighting its potential scalability to even smaller healthcare facilities and to pave the way to access to more medical data for research. This exemplary demonstration of the interplay of different tools provides valuable insights into technical and operational challenges, setting a precedent for future expansions and contributing to the democratization of medical data access.

BACKGROUND: To support research projects that require medical data from multiple sites is one of the goals of the German Medical Informatics Initiative (MII). The data integration centers (DIC) at university medical centers in Germany provide patient data via FHIR® in compliance with the MII core data set (CDS). Requirements for data protection and other legal bases for processing prefer decentralized processing of the relevant data in the DICs and the subsequent exchange of aggregated results for cross-site evaluation.
METHODS: Requirements from clinical experts were obtained in the context of the MII use case INTERPOLAR. A software architecture was then developed, modeled using 3LGM2, finally implemented and published in a github repository.
RESULTS: With the CDS tool chain, we have created software components for decentralized processing on the basis of the MII CDS. The CDS tool chain requires access to a local FHIR endpoint and then transfers the data to an SQL database. This is accessed by the DataProcessor component, which performs calculations with the help of rules (input repo) and writes the results back to the database. The CDS tool chain also has a frontend module (REDCap), which is used to display the output data and calculated results, and allows verification, evaluation, comments and other responses. This feedback is also persisted in the database and is available for further use, analysis or data sharing in the future.
CONCLUSIONS: Other solutions are conceivable. Our solution utilizes the advantages of an SQL database. This enables flexible and direct processing of the stored data using established analysis methods. Due to the modularization, adjustments can be made so that it can be used in other projects. We are planning further developments to support pseudonymization and data sharing. Initial experience is being gathered. An evaluation is pending and planned.

BACKGROUND: Process Mining (PM) has emerged as a transformative tool in healthcare, facilitating the enhancement of process models and predicting potential anomalies. However, the widespread application of PM in healthcare is hindered by the lack of structured event logs and specific data privacy regulations.
METHODS: This paper introduces a pipeline that converts routine healthcare data into PM-compatible event logs, leveraging the newly available permissions under the Health Data Utilization Act to use healthcare data.
METHODS: Our system exploits the Core Data Sets (CDS) provided by Data Integration Centers (DICs). It involves converting routine data into Fast Healthcare Interoperable Resources (FHIR), storing it locally, and subsequently transforming it into standardized PM event logs through FHIR queries applicable on any DIC. This facilitates the extraction of detailed, actionable insights across various healthcare settings without altering existing DIC infrastructures.
CONCLUSIONS: Challenges encountered include handling the variability and quality of data, and overcoming network and computational constraints. Our pipeline demonstrates how PM can be applied even in complex systems like healthcare, by allowing for a standardized yet flexible analysis pipeline which is widely applicable.The successful application emphasize the critical role of tailored event log generation and data querying capabilities in enabling effective PM applications, thus enabling evidence-based improvements in healthcare processes.

暂无摘要。

Hypothesis generation is an early and critical step in any hypothesis-driven clinical research project. Because it is not yet a well-understood cognitive process, the need to improve the process goes unrecognized. Without an impactful hypothesis, the significance of any research project can be questionable, regardless of the rigor or diligence applied in other steps of the study, e.g., study design, data collection, and result analysis. In this perspective article, the authors provide a literature review on the following topics first: scientific thinking, reasoning, medical reasoning, literature-based discovery, and a field study to explore scientific thinking and discovery. Over the years, scientific thinking has shown excellent progress in cognitive science and its applied areas: education, medicine, and biomedical research. However, a review of the literature reveals the lack of original studies on hypothesis generation in clinical research. The authors then summarize their first human participant study exploring data-driven hypothesis generation by clinical researchers in a simulated setting. The results indicate that a secondary data analytical tool, VIADS-a visual interactive analytic tool for filtering, summarizing, and visualizing large health data sets coded with hierarchical terminologies, can shorten the time participants need, on average, to generate a hypothesis and also requires fewer cognitive events to generate each hypothesis. As a counterpoint, this exploration also indicates that the quality ratings of the hypotheses thus generated carry significantly lower ratings for feasibility when applying VIADS. Despite its small scale, the study confirmed the feasibility of conducting a human participant study directly to explore the hypothesis generation process in clinical research. This study provides supporting evidence to conduct a larger-scale study with a specifically designed tool to facilitate the hypothesis-generation process among inexperienced clinical researchers. A larger study could provide generalizable evidence, which in turn can potentially improve clinical research productivity and overall clinical research enterprise.

Amid global health challenges, resilient health systems require continuous innovation and progress. Stakeholders highlight the critical role of digital technologies in accelerating this progress. However, the digital health field faces significant challenges, including the sensitivity of health data, the absence of evidence-based standards, data governance issues, and a lack of evidence on the impact of digital health strategies. Overcoming these challenges is crucial to unlocking the full potential of digital health innovations in enhancing healthcare delivery and outcomes. Prioritizing security and privacy is essential in developing digital health solutions that are transparent, accessible, and effective. Non-fungible tokens (NFTs) have gained widespread attention, including in healthcare, offering innovative solutions and addressing challenges through blockchain technology. This paper addresses the gap in systematic-level studies on NFT applications in healthcare, aiming to comprehensively analyze use cases and associated research challenges. The search included primary studies published between 2014 and November 2023, searching in a balanced set of databases compiling articles from different fields. A review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework and strictly focusing on research articles related to NFT applications in the healthcare sector. The electronic search retrieved 1902 articles, ultimately resulting in 15 articles for data extraction. These articles span applications of NFTs in medical devices, pathology exams, diagnosis, pharmaceuticals, and other healthcare domains, highlighting their potential to eliminate centralized trust sources in health informatics. The review emphasizes the adaptability and versatility of NFT-based solutions, indicating their broader applicability across various healthcare stages and expansion into diverse industries. Given their role in addressing challenges associated with enhancing data integrity, availability, non-repudiation, and authentication, NFTs remain a promising avenue for future research within digital health solutions.

Cancer subtyping refers to categorizing a particular cancer type into distinct subtypes or subgroups based on a range of molecular characteristics, clinical manifestations, histological features, and other relevant factors. The identification of cancer subtypes can significantly enhance precision in clinical practice and facilitate personalized diagnosis and treatment strategies. Recent advancements in the field have witnessed the emergence of numerous network fusion methods aimed at identifying cancer subtypes. The majority of these fusion algorithms, however, solely rely on the fusion network of a single core matrix for the identification of cancer subtypes and fail to comprehensively capture similarity. To tackle this issue, in this study, we propose a novel cancer subtype recognition method, referred to as PCA-constrained multi-core matrix fusion network (PCA-MM-FN). The PCA-MM-FN algorithm initially employs three distinct methods to obtain three core matrices. Subsequently, the obtained core matrices are projected into a shared subspace using principal component analysis, followed by a weighted network fusion. Lastly, spectral clustering is conducted on the fused network. The results obtained from conducting experiments on the mRNA expression, DNA methylation, and miRNA expression of five TCGA datasets and three multi-omics benchmark datasets demonstrate that the proposed PCA-MM-FN approach exhibits superior accuracy in identifying cancer subtypes compared to the existing methods.